INDEX

Explanations

negative or condemning references related to authority and morality from a religious perspective

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

outdir

-0.16

\grid

-0.14

 QuÃ½

-0.14

EMA

-0.14

ãĤ·ãĥ§

-0.14

å¤ªéĥİ

-0.14

UIAlert

-0.14

 ØªØ²

-0.13

 abund

-0.13

Touches

-0.13

POSITIVE LOGITS

ikon

0.15

sport

0.15

 sport

0.14

icina

0.14

cg

0.13

oon

0.13

zug

0.13

odd

0.13

ential

0.13

gross

0.13

Activations Density 0.025%

negative or condemning references related to authority and morality from a religious perspective

No Comments

No Known Activations