INDEX

Explanations

mentions of the word "Car" and its variants in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

arrera

-0.15

inct

-0.15

âĢĮÚ¯

-0.15

arto

-0.15

urement

-0.14

artin

-0.14

urn

-0.14

igkeit

-0.14

oses

-0.14

POSITIVE LOGITS

ibbean

0.19

ldr

0.17

bage

0.17

IDL

0.17

riages

0.16

rying

0.15

TRUE

0.15

nton

0.14

izza

0.14

Ã¤ren

0.14

Activations Density 0.036%

mentions of the word "Car" and its variants in various contexts

No Comments

No Known Activations