INDEX

Explanations

references to health and wellness genres

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 Blasio

-0.17

aley

-0.16

 poil

-0.16

 article

-0.16

ovo

-0.15

é¡ĺãģĦ

-0.15

onu

-0.15

 atas

-0.14

ìĨį

-0.14

ryo

-0.14

POSITIVE LOGITS

 Reference

0.17

Reference

0.16

 Publisher

0.16

 reference

0.15

 general

0.15

_REFERENCE

0.15

 General

0.15

iri

0.15

 specifically

0.14

/reference

0.14

Activations Density 0.008%

references to health and wellness genres

No Comments

No Known Activations