INDEX

Explanations

criteria indicating high quality or standards in various contexts

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

ild

-0.16

BCM

-0.15

 than

-0.15

LEC

-0.15

lez

-0.15

StreamReader

-0.14

Ĺ

-0.14

chet

-0.14

pell

-0.14

net

-0.14

POSITIVE LOGITS

iano

0.16

rix

0.15

ideon

0.14

ãĥĥãĥĦ

0.14

 Yorkers

0.14

ulse

0.14

nger

0.14

ani

0.14

_svc

0.13

conds

0.13

Activations Density 0.112%

criteria indicating high quality or standards in various contexts

No Comments

No Known Activations