INDEX

Explanations

references to health and dietary topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

Ð·Ð½

-0.14

loc

-0.13

stit

-0.13

iei

-0.13

;element

-0.13

coop

-0.13

ipsis

-0.13

quot

-0.13

ãģ¨ãģĨ

-0.13

edu

-0.13

POSITIVE LOGITS

è¥

0.15

aghan

0.15

å¹²

0.15

/gin

0.14

/goto

0.14

ROLLER

0.14

ModelProperty

0.14

å·®

0.13

otype

0.13

arning

0.13

Activations Density 0.009%

references to health and dietary topics

No Comments

No Known Activations