INDEX

Explanations

references to politics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

 Juliet

-0.16

oice

-0.14

arya

-0.14

Ð»Ð°Ð±

-0.14

strict

-0.14

åĤ¬

-0.14

oldemort

-0.13

 Eudicots

-0.13

ÑĮÑİÑĤ

-0.13

aster

-0.13

POSITIVE LOGITS

nish

0.15

oplay

0.14

pline

0.14

egin

0.14

 Ø³Ø±

0.14

itin

0.14

 crowds

0.14

aggio

0.14

rd

0.14

Activations Density 0.007%

references to politics

No Comments

No Known Activations