INDEX

Explanations

numerical values and indicators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

agne

-0.15

Ä°Y

-0.15

ulong

-0.15

weit

-0.13

 wings

-0.13

nid

-0.13

áº±

-0.13

ä»®

-0.13

POSITIVE LOGITS

anova

0.15

inski

0.14

ISCO

0.14

cka

0.14

ãĥ§

0.14

rine

0.14

ESH

0.14

 ÐºÐ¼

0.14

rese

0.13

 Pell

0.13

Activations Density 0.039%

numerical values and indicators

No Comments

No Known Activations