INDEX

Explanations

mentions of specific venues and times

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

vak

-0.15

Ãº

-0.15

é¬¼

-0.15

-0.14

 Superior

-0.14

lama

-0.14

 Memories

-0.14

bourne

-0.13

POSITIVE LOGITS

rats

0.15

odable

0.15

oten

0.15

acey

0.14

lags

0.14

iterated

0.14

å¥Ī

0.14

ãĥ¼ãĥĳ

0.14

ethod

0.14

atus

0.14

Activations Density 0.028%

mentions of specific venues and times

No Comments

No Known Activations