INDEX

Explanations

words related to physical weight or measurements

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

ihn

-0.16

ather

-0.16

 leads

-0.15

asel

-0.15

orris

-0.15

otta

-0.14

olley

-0.14

_dn

-0.14

bic

-0.14

 lead

-0.13

POSITIVE LOGITS

?><

0.16

itan

0.15

?action

0.15

iard

0.15

 Kart

0.15

 BÃ¶l

0.14

PARSE

0.14

UDGE

0.14

otch

0.14

ÙĬÙħØ©

0.14

Activations Density 0.011%

words related to physical weight or measurements

No Comments

No Known Activations