INDEX

Explanations

references to individuals in positions of authority or leadership, specifically chancellors

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

oker

-0.16

CTL

-0.15

fall

-0.15

hog

-0.15

Broad

-0.15

XP

-0.14

_transient

-0.14

inati

-0.14

Immutable

-0.14

fÃ¼h

-0.14

POSITIVE LOGITS

 <!--[

0.16

unik

0.15

ury

0.15

à¤¾à¤¸à¤¨

0.14

neas

0.14

ARENT

0.14

 impro

0.14

_void

0.14

ichick

0.13

Activations Density 0.008%

references to individuals in positions of authority or leadership, specifically chancellors

No Comments

No Known Activations