INDEX

Explanations

words related to intensity, size, and emotional states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

isify

-0.19

$MESS

-0.17

 Leban

-0.15

'gc

-0.15

á¿ĸ

-0.15

uetooth

-0.15

RuleContext

-0.15

weetalert

-0.15

argout

-0.14

Å¡tÄĽnÃŃ

-0.14

POSITIVE LOGITS

 always

0.15

 newly

0.15

0.14

 Irving

0.13

 further

0.13

Ah

0.13

 even

0.13

ë²

0.13

Activations Density 0.018%

words related to intensity, size, and emotional states

No Comments

No Known Activations