INDEX

Explanations

phrases indicating responsibility and accountability in a political context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ãĥ³ãĥĩãĤ£

-0.16

ollen

-0.15

utherford

-0.15

ESSAGES

-0.15

ÅĻev

-0.15

 Branch

-0.14

Ī¬

-0.14

stÃŃ

-0.14

loff

-0.14

klÃ¤

-0.14

POSITIVE LOGITS

anzi

0.15

bakan

0.15

arti

0.15

PIX

0.15

áº¹

0.15

Ë

0.14

eny

0.14

olest

0.14

 Batter

0.14

IFS

0.14

Activations Density 0.011%

phrases indicating responsibility and accountability in a political context

No Comments

No Known Activations