INDEX

Explanations

expressions of opinion or feedback regarding product features and usability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ckill

-0.16

.cf

-0.15

piel

-0.15

illo

-0.15

 æ©Ł

-0.15

().'/

-0.14

 bdsm

-0.14

ancode

-0.14

oÅĻ

-0.14

algo

-0.14

POSITIVE LOGITS

 Bian

0.14

tic

0.14

ntl

0.14

ev

0.13

 keen

0.13

tic

0.13

 Rooney

0.13

Ã¤ft

0.13

-à¤¬

0.13

Activations Density 0.645%

expressions of opinion or feedback regarding product features and usability

No Comments

No Known Activations