INDEX

Explanations

references to appliances and issues associated with them

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

itra

-0.18

itta

-0.16

ialis

-0.16

 True

-0.15

[`

-0.14

 Cran

-0.14

ugo

-0.14

lesh

-0.14

irts

-0.14

POSITIVE LOGITS

osate

0.20

bedo

0.18

xab

0.16

pev

0.15

ascript

0.15

-pt

0.14

simd

0.14

prite

0.14

ixo

0.14

_phr

0.14

Activations Density 0.373%

references to appliances and issues associated with them

No Comments

No Known Activations