INDEX

Explanations

phrases indicating unsupported or unimplemented features in code

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

otten

-0.17

run

-0.15

tones

-0.15

 Manning

-0.15

Ott

-0.14

iesen

-0.14

aisal

-0.14

ØªØ²

-0.14

çª

-0.14

wat

-0.14

POSITIVE LOGITS

pedia

0.14

urtle

0.14

Î·Î³

0.14

éĻ°

0.14

edException

0.14

ohl

0.14

pdata

0.14

ynes

0.13

çĶ

0.13

Activations Density 0.015%

phrases indicating unsupported or unimplemented features in code

No Comments

No Known Activations