INDEX

Explanations

specific locations and references related to various fields, including technology, music, and community engagement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

uber

-0.16

æµ¦

-0.15

 cuckold

-0.15

ivr

-0.15

undos

-0.15

pageTitle

-0.14

eyse

-0.14

Ka

-0.14

 Horton

-0.14

POSITIVE LOGITS

hunt

0.14

swana

0.14

íı°

0.14

ainter

0.14

emes

0.14

fcn

0.14

 ones

0.14

ocom

0.13

çŃĨ

0.13

aju

0.13

Activations Density 0.077%

specific locations and references related to various fields, including technology, music, and community engagement

No Comments

No Known Activations