INDEX

Explanations

terms that describe standard or typical features and characteristics

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

unar

-0.15

 Braun

-0.15

newInstance

-0.15

upe

-0.14

echn

-0.14

ichten

-0.14

ampa

-0.13

_NAMESPACE

-0.13

ichen

-0.13

undry

-0.13

POSITIVE LOGITS

ordinary

0.19

 ordinary

0.18

-sized

0.17

 æĻ®éĢļ

0.16

ily

0.16

æĻ®éĢļ

0.16

egov

0.16

/common

0.15

(non

0.15

 ØªØµÙħ

0.15

Activations Density 0.121%

terms that describe standard or typical features and characteristics

No Comments

No Known Activations