INDEX

Explanations

actions related to acquiring, viewing, or learning about items, particularly in a shopping or information-seeking context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ule

-0.15

ieri

-0.15

 pars

-0.15

ØªØ±ÛĮ

-0.14

be

-0.14

Mev

-0.14

↵

-0.14

angi

-0.14

uten

-0.14

ansa

-0.14

POSITIVE LOGITS

osite

0.16

çĬ

0.15

CORD

0.15

@js

0.14

iture

0.14

/stream

0.14

Field

0.14

UZ

0.14

 liá»ĩu

0.14

 Field

0.13

Activations Density 0.069%

actions related to acquiring, viewing, or learning about items, particularly in a shopping or information-seeking context

No Comments

No Known Activations