INDEX

Explanations

descriptions of properties and reflections about experiences or observations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ÎºÎ¬

-0.15

obel

-0.15

igo

-0.15

nesc

-0.15

baugh

-0.14

IGO

-0.14

enko

-0.14

.ds

-0.14

aro

-0.14

POSITIVE LOGITS

 rather

0.20

 than

0.19

rather

0.18

 Rather

0.17

eyh

0.15

Rather

0.15

ddl

0.15

li

0.15

-than

0.15

FY

0.15

Activations Density 0.183%

descriptions of properties and reflections about experiences or observations

No Comments

No Known Activations