INDEX

Explanations

names of films and associated production details

oai_token-act-pair · gpt-4o-mini Triggered by @bot

proper nouns, particularly names of people, places, brands, and titles.

oai_token-act-pair · claude-4-5-sonnet Triggered by @jyhe0408

proper nouns, especially names and titles of people, places, organizations, brands, and entertainment works.

oai_token-act-pair · gpt-5 Triggered by @jyhe0408

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

umann

-0.16

ebra

-0.15

Alg

-0.14

pac

-0.14

iser

-0.14

iblings

-0.14

Å¡etÅĻ

-0.13

Âł

-0.13

ureau

-0.13

POSITIVE LOGITS

 Hammond

0.15

 lesbi

0.14

åĿ¡

0.14

 ((__

0.14

macros

0.14

é³´

0.13

 nues

0.13

ÑĶÐ²

0.13

 Seks

0.13

avit

0.13

Activations Density 0.220%

names of films and associated production details

proper nouns, particularly names of people, places, brands, and titles.

proper nouns, especially names and titles of people, places, organizations, brands, and entertainment works.

No Comments

No Known Activations