INDEX

Explanations

references to academic publications and authors

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

phia

-0.15

uth

-0.15

angen

-0.14

 Hubb

-0.14

ican

-0.13

pun

-0.13

Ð±Ð°Ñĩ

-0.13

odge

-0.13

ulu

-0.13

untu

-0.13

POSITIVE LOGITS

 Neck

0.18

Î³Î¿Ïį

0.16

Ð¼Ñĸ

0.14

HeaderValue

0.14

agli

0.14

ilha

0.14

ceu

0.14

egin

0.14

-neck

0.14

ertools

0.14

Activations Density 0.058%

references to academic publications and authors

No Comments

No Known Activations