INDEX

Explanations

references to specific car models and their characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

SURE

-0.14

eo

-0.14

["@

-0.14

 knex

-0.13

.toJson

-0.13

readcr

-0.13

èĩ

-0.13

IMPLEMENT

-0.13

 sonu

-0.13

POSITIVE LOGITS

 factory

0.16

 ownership

0.15

 original

0.15

avern

0.15

dyn

0.15

 Rally

0.15

/documentation

0.15

.factory

0.15

 Borg

0.15

 Inspection

0.14

Activations Density 0.017%

references to specific car models and their characteristics

No Comments

No Known Activations