INDEX

Explanations

references to video content or media presentations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

Å¾iv

-0.16

prit

-0.16

resher

-0.15

orsche

-0.15

ãĥ©ãĤ¤ãĥ³

-0.14

ioned

-0.14

zen

-0.14

ÐºÐ¸Ð½

-0.14

ught

-0.14

 Kraft

-0.13

POSITIVE LOGITS

ÐµÐ³Ð¾ÑĢ

0.16

à¸Ķà¸ĩ

0.15

suspend

0.15

/browse

0.14

undef

0.14

kinson

0.14

_BOTH

0.14

ombok

0.14

ovice

0.14

 Mour

0.14

Activations Density 0.052%

references to video content or media presentations

No Comments

No Known Activations