INDEX

Explanations

phrases indicating the appropriateness or compatibility of items for specific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ni

-0.15

acock

-0.15

ãģ«ãģĭ

-0.15

alie

-0.14

nak

-0.14

ache

-0.14

acie

-0.14

acles

-0.13

 Howell

-0.13

.il

-0.13

POSITIVE LOGITS

quine

0.17

etting

0.16

chunk

0.15

æľĭ

0.15

ripe

0.15

ritz

0.15

kening

0.14

DirectoryName

0.14

ĺ

0.14

-issue

0.14

Activations Density 0.007%

phrases indicating the appropriateness or compatibility of items for specific contexts

No Comments

No Known Activations