INDEX

Explanations

references to political representatives and legislative discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

enate

-0.17

 Senate

-0.16

æ·

-0.15

rient

-0.15

 Capitol

-0.15

Senate

-0.14

vyk

-0.14

lassen

-0.14

skin

-0.14

down

-0.14

POSITIVE LOGITS

Rep

0.18

Rep

0.17

unes

0.16

igm

0.15

 noqa

0.15

ÐµÑĢÐ°Ð»ÑĮ

0.15

GetMethod

0.15

abbo

0.15

ulen

0.15

Activations Density 0.029%

references to political representatives and legislative discussions

No Comments

No Known Activations