INDEX

Explanations

vehicle-related terms and specific car models

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

aires

-0.15

packing

-0.15

 dist

-0.14

 prof

-0.14

 distilled

-0.14

/dist

-0.14

 (*((

-0.14

scal

-0.14

ptune

-0.13

POSITIVE LOGITS

åŃ£

0.17

enal

0.15

áºŃp

0.15

isz

0.14

Ã³m

0.14

ungs

0.14

RAIN

0.14

äºĴ

0.14

.dense

0.14

 Cham

0.14

Activations Density 0.257%

vehicle-related terms and specific car models

No Comments

No Known Activations