INDEX

Explanations

specific identifiers and attributes related to resources or elements in programming or web contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

-0.17

-0.15

.Private

-0.15

-0.14

rika

-0.14

ocha

-0.14

exc

-0.14

-0.13

rene

-0.13

POSITIVE LOGITS

PELL

0.16

uthor

0.14

Å¡k

0.13

oli

0.13

/repository

0.13

kins

0.13

ptest

0.13

 Vapor

0.13

Bid

0.13

 favour

0.13

Activations Density 0.107%

specific identifiers and attributes related to resources or elements in programming or web contexts

No Comments

No Known Activations