INDEX

Explanations

phrases indicating continuation or persistence in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

rray

-0.15

ÑıÐ³

-0.15

illaume

-0.14

onavir

-0.14

.scenes

-0.14

rale

-0.14

 Blitz

-0.14

 Ð´ÑĢ

-0.14

æĿ¾

-0.14

/XMLSchema

-0.14

POSITIVE LOGITS

ovan

0.17

sembl

0.17

Cad

0.17

Cad

0.16

0.15

cken

0.15

Ã¼ss

0.15

ai

0.14

Activations Density 0.157%

phrases indicating continuation or persistence in various contexts

No Comments

No Known Activations