INDEX

Explanations

concepts related to representation and the distillation of truth

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

adge

-0.17

ambi

-0.17

eydi

-0.15

andest

-0.15

Ø±Ø§Øª

-0.14

lÃŃÄį

-0.14

ijo

-0.14

Ľå»º

-0.14

ulp

-0.13

aben

-0.13

POSITIVE LOGITS

Äĵ

0.14

aman

0.14

ema

0.13

icha

0.13

aml

0.13

 humans

0.13

 Humans

0.13

 Caucus

0.13

Activations Density 0.372%

concepts related to representation and the distillation of truth

No Comments

No Known Activations