INDEX

Explanations

coding-related terms and phrases, particularly documentation or descriptions

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

ãĤ©

-0.17

igh

-0.17

aut

-0.17

issa

-0.16

ial

-0.16

opi

-0.15

å¸ģ

-0.15

au

-0.15

atabase

-0.14

aus

-0.14

POSITIVE LOGITS

rvine

0.18

ewood

0.17

ght

0.17

VERS

0.16

 dá»¥

0.15

iado

0.15

pped

0.15

erten

0.15

ÅĽmy

0.15

Activations Density 0.056%

coding-related terms and phrases, particularly documentation or descriptions

No Comments

No Known Activations