INDEX

Explanations

references to various foundations and their activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

oline

-0.18

reff

-0.18

union

-0.16

ingen

-0.16

 Foundation

-0.16

-0.15

sik

-0.15

isions

-0.15

baz

-0.15

asso

-0.15

POSITIVE LOGITS

ally

0.20

ality

0.19

aries

0.18

lation

0.17

lay

0.17

ary

0.17

arity

0.17

/Foundation

0.17

aire

0.17

hei

0.16

Activations Density 0.021%

references to various foundations and their activities

No Comments

No Known Activations