INDEX

Explanations

names of authors and contributors in academic contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

zh

-0.16

 å¾Ĵ

-0.15

pair

-0.14

ASSES

-0.14

æ¬ł

-0.14

orst

-0.14

æ¼Ķ

-0.14

illez

-0.14

Movies

-0.13

utas

-0.13

POSITIVE LOGITS

Î¼Î¼Îµ

0.16

 counsel

0.15

sw

0.15

 carry

0.15

 carries

0.14

 carrying

0.14

sit

0.14

 wider

0.13

 guide

0.13

icker

0.13

Activations Density 0.174%

names of authors and contributors in academic contexts

No Comments

No Known Activations