INDEX

Explanations

proper nouns and references to journalists or news sources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

astes

-0.15

á»±c

-0.14

urette

-0.14

åĬŁ

-0.14

amus

-0.14

_completion

-0.14

 frequ

-0.14

oni

-0.14

PDF

-0.14

rossover

-0.13

POSITIVE LOGITS

Enlarge

0.18

ØºØ§Ø²

0.15

obia

0.14

nowrap

0.14

utan

0.14

PathComponent

0.14

ÑĢÐµÑħ

0.14

anj

0.14

inder

0.14

ivan

0.14

Activations Density 0.010%

proper nouns and references to journalists or news sources

No Comments

No Known Activations