INDEX

Explanations

key events, shows, or performances mentioned in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

yon

-0.15

otu

-0.14

gradation

-0.13

ekli

-0.13

asso

-0.13

vrd

-0.13

Ð¾Ð»Ð¶

-0.13

ksi

-0.13

atern

-0.13

fad

-0.13

POSITIVE LOGITS

 features

0.93

 feature

0.90

features

0.81

 Features

0.81

feature

0.77

Features

0.74

 Feature

0.74

-feature

0.72

Feature

0.71

 FEATURES

0.68

Activations Density 0.203%

key events, shows, or performances mentioned in the text

No Comments

No Known Activations