INDEX

Explanations

phrases and terms related to broad concepts and their implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

asl

-0.14

onavir

-0.14

jing

-0.14

adu

-0.13

iten

-0.13

uur

-0.13

foil

-0.13

é¾Ħ

-0.13

bjerg

-0.13

ints

-0.12

POSITIVE LOGITS

 cover

0.83

 covers

0.80

 covering

0.77

 Cover

0.76

Cover

0.73

 covered

0.71

cover

0.70

-cover

0.70

 Covers

0.69

covers

0.67

Activations Density 0.478%

phrases and terms related to broad concepts and their implications

No Comments

No Known Activations