INDEX

Explanations

references to legal and political issues

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

ÃŃl

-0.17

egment

-0.16

vais

-0.16

irut

-0.15

riba

-0.15

/Dk

-0.15

avad

-0.15

ÑĥÑĩÐ°

-0.14

estic

-0.14

.gg

-0.14

POSITIVE LOGITS

th

0.15

itus

0.15

 Vern

0.14

icon

0.14

 Verm

0.14

TM

0.14

Oz

0.14

Ric

0.13

foo

0.13

soy

0.13

Activations Density 0.301%

references to legal and political issues

No Comments

No Known Activations