INDEX

Explanations

references to vectors in mathematical or programming contexts, specifically those related to their properties and usage

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

cec

-0.15

elines

-0.15

chl

-0.14

ough

-0.14

arna

-0.14

angan

-0.14

ANGUAGE

-0.14

.bn

-0.14

neh

-0.14

ê

-0.14

POSITIVE LOGITS

.ERR

0.15

Lie

0.15

ohn

0.15

pins

0.14

wert

0.14

 Pron

0.14

Ø±ÛĮØ²

0.13

inos

0.13

íĺ

0.13

.Apis

0.13

Activations Density 0.010%

references to vectors in mathematical or programming contexts, specifically those related to their properties and usage

No Comments

No Known Activations