INDEX

Explanations

numerical data and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

 Ä°st

-0.17

stad

-0.15

GENER

-0.15

ewan

-0.14

Rae

-0.14

umblr

-0.14

stadt

-0.14

Fat

-0.14

idlo

-0.13

mul

-0.13

POSITIVE LOGITS

ÑģÐµÐ½

0.15

ins

0.15

 Bottom

0.14

asive

0.14

Kov

0.14

hire

0.14

unittest

0.13

chemy

0.13

ouver

0.13

avirus

0.13

Activations Density 0.058%

numerical data and statistics

No Comments

No Known Activations