INDEX

Explanations

references to characters and their roles in stories

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

ieux

-0.15

getLocale

-0.14

á¿

-0.14

ior

-0.14

IOR

-0.13

 Accessed

-0.13

/INFO

-0.13

bor

-0.13

 @"↵

-0.13

/access

-0.13

POSITIVE LOGITS

 appearing

0.77

 appear

0.73

 appears

0.73

 appearance

0.72

 appeared

0.72

 appearances

0.70

 apare

0.67

appear

0.63

 Appearance

0.63

 Appears

0.58

Activations Density 0.309%

references to characters and their roles in stories

No Comments

No Known Activations