INDEX

Explanations

dates and times

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

lier

-0.17

 atIndex

-0.16

 **************************************************************************

-0.15

iste

-0.14

ÙĬÙĬÙĨ

-0.14

 nextState

-0.14

leine

-0.14

/plugins

-0.14

 Waters

-0.13

ÏĢÎµ

-0.13

POSITIVE LOGITS

jong

0.15

ngen

0.15

ConnectionFactory

0.15

jom

0.14

egra

0.14

lick

0.14

 Carter

0.14

MOTE

0.14

xes

0.14

Activations Density 0.008%

dates and times

No Comments

No Known Activations