INDEX

Explanations

numerical data or statistics in a structured format, possibly related to research

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

kins

-0.15

esini

-0.14

ÅĽci

-0.14

ongyang

-0.14

Ø®Ø±

-0.14

auce

-0.14

ason

-0.14

asso

-0.14

Umb

-0.13

 Tier

-0.13

POSITIVE LOGITS

âĪ¨

0.15

Responder

0.14

SOP

0.14

otos

0.14

OwnerId

0.14

CTYPE

0.13

æĪ²

0.13

ukan

0.13

Powered

0.13

erea

0.13

Activations Density 0.003%

numerical data or statistics in a structured format, possibly related to research

No Comments

No Known Activations