INDEX

Explanations

discussions related to criticism and analysis of cultural content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

Ã¼lt

-0.15

 trivia

-0.15

allo

-0.15

 Crud

-0.15

Documentation

-0.15

ston

-0.14

 Wikipedia

-0.14

enez

-0.14

kuk

-0.13

 crud

-0.13

POSITIVE LOGITS

 article

0.20

op

0.18

($)

0.18

 essay

0.17

 columns

0.16

essay

0.16

æĺ¨

0.16

SND

0.16

 column

0.15

 trench

0.15

Activations Density 0.250%

discussions related to criticism and analysis of cultural content

No Comments

No Known Activations