INDEX

Explanations

proper nouns, specifically names of people and awards

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

STRU

-0.15

 Reese

-0.15

 Bilg

-0.14

GENCY

-0.14

gens

-0.14

otherwise

-0.14

 Pron

-0.14

-0.13

uby

-0.13

verted

-0.13

POSITIVE LOGITS

owie

0.16

ovny

0.16

 decision

0.16

DW

0.15

ç¸

0.15

DM

0.15

ream

0.15

 Decision

0.15

ynom

0.15

_dm

0.14

Activations Density 0.030%

proper nouns, specifically names of people and awards

No Comments

No Known Activations