INDEX

Explanations

references to political representatives and government officials

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

osate

-0.16

hausen

-0.14

ÐµÑĢÐµÑĩ

-0.14

anker

-0.14

EMENT

-0.14

ness

-0.14

pped

-0.14

è¶

-0.14

hs

-0.14

ivent

-0.14

POSITIVE LOGITS

let

0.14

eca

0.14

::__

0.13

 Brewer

0.13

 draft

0.13

 Slam

0.13

-elect

0.13

 Pers

0.13

 Lawson

0.13

eneral

0.13

Activations Density 0.018%

references to political representatives and government officials

No Comments

No Known Activations