INDEX

Explanations

terms related to car models and their features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

.scalablytyped

-0.18

cly

-0.16

profession

-0.15

Î¼Î¼

-0.15

ä½³

-0.15

.dtd

-0.15

grading

-0.14

IGHL

-0.14

abd

-0.14

-Clause

-0.14

POSITIVE LOGITS

0.15

anno

0.14

UTE

0.14

 Westbrook

0.14

fir

0.14

(MPI

0.14

com

0.14

anh

0.13

 Ziel

0.13

 mild

0.13

Activations Density 0.178%

terms related to car models and their features

No Comments

No Known Activations