INDEX

Explanations

phrases expressing conditional scenarios or choices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

XObject

-0.16

 stuff

-0.15

?><

-0.15

umu

-0.15

-0.14

seau

-0.14

ewater

-0.14

UPI

-0.14

roid

-0.14

avic

-0.13

POSITIVE LOGITS

 olursa

0.16

ä¿Ĭ

0.14

nor

0.14

 dabei

0.14

 ÙħØ´Ø§Ø±

0.14

OMEM

0.14

itzer

0.14

Äįer

0.14

whether

0.14

Activations Density 0.047%

phrases expressing conditional scenarios or choices

No Comments

No Known Activations