INDEX

Explanations

numerical values and associated units of measurement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

azen

-0.15

ombo

-0.15

atz

-0.15

áº£y

-0.14

acob

-0.14

oit

-0.14

 spectacle

-0.14

anking

-0.14

acin

-0.14

andÄ±r

-0.14

POSITIVE LOGITS

'gc

0.14

ilar

0.14

Ãºblica

0.14

contres

0.13

 imperson

0.13

onica

0.13

uard

0.13

 unconscious

0.13

ullet

0.13

 Bare

0.12

Activations Density 0.007%

numerical values and associated units of measurement

No Comments

No Known Activations