INDEX

Explanations

references to roles and contributions in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

rese

-0.17

ophobia

-0.15

less

-0.15

ãĥ¼ãĥĩ

-0.14

ville

-0.14

obo

-0.14

wash

-0.14

 lift

-0.14

udeau

-0.14

ubar

-0.14

POSITIVE LOGITS

 forall

0.16

regor

0.15

ÏĥÎ¯

0.14

Ð°ÑĤÐºÐ¸

0.14

elon

0.14

WithPath

0.13

Matchers

0.13

YLE

0.13

 Xiao

0.13

ìĩ¼

0.13

Activations Density 0.873%

references to roles and contributions in various contexts

No Comments

No Known Activations