INDEX

Explanations

instances of individuals or topics being publicly discussed or brought to attention

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ongyang

-0.16

mare

-0.15

Riy

-0.14

 Lebens

-0.14

ayne

-0.14

iyon

-0.14

emphasis

-0.13

á»ĳt

-0.13

observeOn

-0.13

Î³Î¬

-0.13

POSITIVE LOGITS

 publicly

0.20

 pÃºblica

0.19

 about

0.17

.public

0.16

public

0.16

 openly

0.15

 pÃºb

0.15

 public

0.15

/public

0.15

(public

0.14

Activations Density 0.080%

instances of individuals or topics being publicly discussed or brought to attention

No Comments

No Known Activations