INDEX

Explanations

concepts related to personal uniqueness and self-improvement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

bart

-0.17

_firestore

-0.15

@}

-0.15

JsonValue

-0.14

xda

-0.14

compass

-0.14

indsight

-0.14

)((((

-0.14

 ÙĦØº

-0.14

@a

-0.13

POSITIVE LOGITS

umper

0.15

 bundles

0.15

 conf

0.14

sil

0.14

 then

0.14

 æ¢

0.14

IVE

0.14

 Bund

0.14

uar

0.14

 bundle

0.14

Activations Density 0.085%

concepts related to personal uniqueness and self-improvement

No Comments

No Known Activations