INDEX

Explanations

mentions of individuals in positions of authority or leadership, particularly those holding the title "deputy."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ulan

-0.16

kla

-0.16

_utilities

-0.15

usk

-0.15

 ÑįÐ»ÐµÐº

-0.14

ç»©

-0.14

 {?>↵

-0.14

zones

-0.14

orro

-0.14

ãĢģãĢģ

-0.14

POSITIVE LOGITS

ature

0.16

ship

0.16

ure

0.15

/full

0.15

ships

0.15

ny

0.14

ido

0.14

bh

0.14

ats

0.14

cum

0.14

Activations Density 0.026%

mentions of individuals in positions of authority or leadership, particularly those holding the title "deputy."

No Comments

No Known Activations