INDEX

Explanations

actions or processes involving goals and requirements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ModelProperty

-0.17

asti

-0.15

ington

-0.15

INGTON

-0.14

irth

-0.14

ÐµÑĩ

-0.14

Ø±ÛĮÙħ

-0.14

izza

-0.14

ober

-0.13

 Glover

-0.13

POSITIVE LOGITS

æīįèĥ½

0.22

ursal

0.15

lero

0.15

lsen

0.15

 má»Ľi

0.15

ibri

0.15

 effective

0.15

AccessException

0.15

otope

0.14

ourke

0.14

Activations Density 0.100%

actions or processes involving goals and requirements

No Comments

No Known Activations