INDEX

Explanations

names of individuals and specific organizations

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

etc

-0.14

undy

-0.14

etc

-0.14

 Ekon

-0.14

RLF

-0.13

ledged

-0.13

 Commonwealth

-0.13

iona

-0.13

itten

-0.12

essen

-0.12

POSITIVE LOGITS

 thuá»Ļc

0.14

ëĳĺ

0.14

kers

0.14

atories

0.14

 ",",

0.13

$/,

0.13

apiro

0.13

 speaking

0.13

nic

0.13

 head

0.12

Activations Density 0.041%

names of individuals and specific organizations

No Comments

No Known Activations