INDEX

Explanations

assertive statements about the qualities or characteristics of various subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

aru

-0.15

isch

-0.15

insky

-0.14

atos

-0.14

oller

-0.14

 otherwise

-0.14

UTE

-0.14

pt

-0.14

çĶļèĩ³

-0.13

 typical

-0.13

POSITIVE LOGITS

oriously

0.16

 inherently

0.16

 notoriously

0.16

OutOfRangeException

0.15

bih

0.15

 famously

0.14

-UA

0.14

istar

0.14

linger

0.14

ConverterFactory

0.14

Activations Density 0.301%

assertive statements about the qualities or characteristics of various subjects

No Comments

No Known Activations