INDEX

Explanations

references to San Francisco

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

istrovstvÃŃ

-0.17

-0.15

koa

-0.14

Vo

-0.14

ingu

-0.14

orf

-0.14

stands

-0.13

Lie

-0.13

 pict

-0.13

Ø·ÙĨ

-0.13

POSITIVE LOGITS

bÃŃr

0.16

 copp

0.15

odo

0.14

igin

0.14

.Kind

0.14

 Biology

0.13

Sharper

0.13

lev

0.13

 condi

0.13

ething

0.13

Activations Density 0.003%

references to San Francisco

No Comments

No Known Activations