INDEX

Explanations

statistical figures and numerical data related to various topics

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

Boh

-0.18

-toggler

-0.18

lied

-0.16

-0.15

ÎµÏį

-0.15

 Neutral

-0.15

 Mein

-0.15

 neutrality

-0.15

iero

-0.14

ëŁ°

-0.14

POSITIVE LOGITS

icer

0.16

ulin

0.15

phem

0.15

SCRIPTOR

0.14

annon

0.14

 æķ

0.14

igr

0.14

_formatted

0.13

ikel

0.13

ovel

0.13

Activations Density 0.272%

statistical figures and numerical data related to various topics

No Comments

No Known Activations

statistical figures and numerical data related to various topics

No Comments

No Known Activations