INDEX

Explanations

sections of code with varying levels of structure and organization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

zÃ¡

-0.16

irie

-0.16

ercul

-0.15

mt

-0.15

æ³

-0.15

 dwarf

-0.14

inel

-0.14

à¹Īà¸§à¸ĩ

-0.14

ottie

-0.14

 Signed

-0.14

POSITIVE LOGITS

 else

0.15

çĵľ

0.15

quet

0.15

ë§Ľ

0.14

_lineno

0.14

elsif

0.14

 jclass

0.14

æµ¦

0.14

Å¡t

0.14

.getvalue

0.14

Activations Density 0.023%

sections of code with varying levels of structure and organization

No Comments

No Known Activations