INDEX

Explanations

attributes related to quality and classification of products or entities

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

.Automation

-0.15

serter

-0.15

iley

-0.14

yu

-0.13

hoff

-0.13

izm

-0.13

quiry

-0.13

Odd

-0.13

igo

-0.12

Cube

-0.12

POSITIVE LOGITS

prec

0.16

anza

0.15

 Prec

0.14

 tarihli

0.14

Ã²i

0.14

 Carpenter

0.13

 Pitt

0.13

_prec

0.13

PREC

0.13

Activations Density 0.113%

attributes related to quality and classification of products or entities

No Comments

No Known Activations