INDEX

Explanations

references to specific organizations, institutions, or brands

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

è¾º

-0.16

ë°©

-0.15

ë¥ĺ

-0.14

URRED

-0.14

olean

-0.14

prar

-0.14

Ð¾ÑĢÐ¾Ð´

-0.14

ennen

-0.14

etail

-0.13

ensis

-0.13

POSITIVE LOGITS

Ð¾Ð´Ñĥ

0.15

 âŀ

0.13

è®

0.13

 Pornhub

0.12

obia

0.12

Â»:

0.12

KB

0.12

BF

0.12

 fung

0.12

Activations Density 0.373%

references to specific organizations, institutions, or brands

No Comments

No Known Activations