INDEX

Explanations

proper nouns, particularly names of individuals

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

agger

-0.14

ilis

-0.14

adro

-0.14

ç«ľ

-0.14

-0.13

ately

-0.13

 leveling

-0.13

_tf

-0.13

ceed

-0.13

 ----------------------------------------------------------------------↵

-0.13

POSITIVE LOGITS

tent

0.16

QUIRED

0.15

ÑĢÐµÐ±

0.14

 Petit

0.14

REW

0.13

/modal

0.13

isters

0.13

stddef

0.13

icont

0.13

uka

0.13

Activations Density 0.017%

proper nouns, particularly names of individuals

No Comments

No Known Activations