INDEX

Explanations

occurrences of numerical values within a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

undi

-0.15

arti

-0.15

'..

-0.14

cky

-0.14

 Curl

-0.14

fh

-0.14

 ÑĤÐµÑĩ

-0.14

ithmetic

-0.14

aley

-0.14

 cÃ´t

-0.14

POSITIVE LOGITS

owa

0.17

_bt

0.16

ä½ı

0.16

OPY

0.16

 Sesso

0.15

rig

0.15

ElementsBy

0.15

 éģ

0.15

 rall

0.15

emy

0.15

Activations Density 0.000%

occurrences of numerical values within a document

No Comments

No Known Activations