INDEX

Explanations

references to lobbying and lobbyists

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ume

-0.16

oader

-0.15

 Templ

-0.15

ooke

-0.15

á»¡

-0.15

bucks

-0.15

 Howell

-0.15

iber

-0.14

ekyll

-0.13

POSITIVE LOGITS

 antenn

0.15

åĹ

0.15

atar

0.15

0.14

ARENT

0.14

staw

0.14

sten

0.14

rl

0.14

oru

0.14

Activations Density 0.009%

references to lobbying and lobbyists

No Comments

No Known Activations