INDEX

Explanations

references to individuals in various contexts and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

icha

-0.17

ropp

-0.16

kud

-0.14

æŃ

-0.14

ç»

-0.14

adoo

-0.13

æĪª

-0.13

figur

-0.13

à¸´à¹Ī

-0.13

ãĥ¼ãĥĢ

-0.12

POSITIVE LOGITS

 center

0.57

 centre

0.54

 left

0.52

 right

0.43

center

0.43

far

0.42

centre

0.41

left

0.41

-center

0.38

 foreground

0.38

Activations Density 0.099%

references to individuals in various contexts and events

No Comments

No Known Activations