INDEX

Explanations

references to authority and control in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

arella

-0.17

uario

-0.16

ickets

-0.16

OMIC

-0.15

abei

-0.14

æĨ

-0.14

AEA

-0.14

ãģķãĤī

-0.14

 ÑĦÑĥÐ½Ð´Ð°

-0.14

idUser

-0.14

POSITIVE LOGITS

ÑģÐ»Ð¸

0.16

odies

0.16

chs

0.15

chied

0.14

encial

0.14

 spotted

0.14

 dich

0.14

Impl

0.14

Activations Density 0.026%

references to authority and control in various contexts

No Comments

No Known Activations