INDEX

Explanations

numerical representations related to assessments or evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

-0.14

anos

-0.14

 Source

-0.14

eless

-0.14

etzt

-0.14

ÐµÑĢ

-0.14

uhe

-0.14

 sources

-0.13

 source

-0.13

POSITIVE LOGITS

opher

0.15

åĽ

0.14

-UA

0.14

)prepare

0.13

vu

0.13

foil

0.13

alement

0.12

INY

0.12

-hooks

0.12

!č↵

0.12

Activations Density 1.449%

numerical representations related to assessments or evaluations

No Comments

No Known Activations