INDEX

Explanations

references to news articles and stories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

sou

-0.17

err

-0.16

urgy

-0.16

 senses

-0.15

erry

-0.15

 sens

-0.15

 fuel

-0.15

 base

-0.14

 pass

-0.14

POSITIVE LOGITS

ä¸Ī

0.17

/TT

0.15

icker

0.15

aign

0.15

aminer

0.15

@update

0.15

leet

0.15

iddy

0.14

/state

0.14

paque

0.14

Activations Density 0.027%

references to news articles and stories

No Comments

No Known Activations