INDEX

Explanations

concepts related to criticism and discourse

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

Ð»ÐµÐ¶

-0.17

antal

-0.16

ç«ĭãģ¦

-0.16

pire

-0.14

æļ®

-0.14

orum

-0.14

eliminar

-0.14

 ÄĳÃ³ng

-0.13

à¸Ńà¸ļ

-0.13

legen

-0.13

POSITIVE LOGITS

str

0.50

dev

0.50

ve

0.49

 stray

0.42

 diver

0.37

 deviation

0.35

 branching

0.35

 branch

0.35

 Branch

0.34

branch

0.33

Activations Density 0.395%

concepts related to criticism and discourse

No Comments

No Known Activations