INDEX

Explanations

references to physical positioning or proximity in relation to people or objects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

semb

-0.17

 Classified

-0.16

icense

-0.15

 stripslashes

-0.15

imas

-0.15

AdapterFactory

-0.15

illos

-0.15

isses

-0.15

thic

-0.14

Enum

-0.14

POSITIVE LOGITS

/in

0.15

yte

0.15

 Marsh

0.15

unh

0.14

 Quarterly

0.14

sold

0.14

ysqli

0.14

zilla

0.14

ãģĤ

0.14

Activations Density 0.028%

references to physical positioning or proximity in relation to people or objects

No Comments

No Known Activations