INDEX

Explanations

structures and architectural elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ivan

-0.16

ially

-0.15

mando

-0.14

 cole

-0.14

ossal

-0.14

çŀ

-0.14

alous

-0.13

çī©

-0.13

ively

-0.13

POSITIVE LOGITS

 secs

0.17

illage

0.17

eron

0.15

 Courts

0.15

sons

0.15

 artificial

0.14

 courts

0.14

 flexible

0.14

 robust

0.14

itters

0.14

Activations Density 0.087%

structures and architectural elements

No Comments

No Known Activations