INDEX

Explanations

numerical data or statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

------+------+

-0.16

imenti

-0.15

 hind

-0.15

fir

-0.15

dl

-0.14

ÐµÐ³Ð¾ÑĢ

-0.14

 Precision

-0.14

æĻĤä»£

-0.14

fir

-0.14

 Ahead

-0.14

POSITIVE LOGITS

 Blanco

0.16

Ð°Ð½Ðº

0.13

Lean

0.13

ĳľ

0.13

rite

0.13

ÏİÎ½Î±

0.13

atern

0.13

eng

0.13

ication

0.13

$MESS

0.13

Activations Density 0.022%

numerical data or statistics

No Comments

No Known Activations