INDEX

Explanations

references to specific individuals or entities in a community context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

uzu

-0.15

otime

-0.15

outh

-0.15

ew

-0.14

pio

-0.14

Ð¦Ðµ

-0.14

lien

-0.14

udu

-0.14

Pew

-0.14

za

-0.14

POSITIVE LOGITS

etc

0.15

_Source

0.15

 respectively

0.15

 thÃ¬

0.15

omik

0.14

ffi

0.14

tte

0.14

mobx

0.14

@testable

0.13

Activations Density 0.194%

references to specific individuals or entities in a community context

No Comments

No Known Activations