INDEX

Explanations

terms associated with automotive and racing contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

sob

-0.16

Outlet

-0.14

aber

-0.14

åº§

-0.14

ħ

-0.14

eid

-0.13

 Äĳá»ĭa

-0.13

roi

-0.13

 tant

-0.13

ä½ķ

-0.13

POSITIVE LOGITS

bai

0.14

indo

0.14

gli

0.14

PING

0.14

æģ¯

0.14

 deep

0.14

Å¡ov

0.13

upported

0.13

bie

0.13

Activations Density 0.028%

terms associated with automotive and racing contexts

No Comments

No Known Activations