INDEX

Explanations

names and references related to individuals and their achievements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

imento

-0.18

innen

-0.15

ocular

-0.15

imenti

-0.15

ascus

-0.14

avou

-0.14

cmc

-0.14

fires

-0.14

aments

-0.14

Deg

-0.14

POSITIVE LOGITS

/ge

0.26

rical

0.19

ally

0.18

Î¡Îĵ

0.17

ebra

0.16

Ge

0.16

roi

0.16

auga

0.15

ffen

0.15

Ge

0.15

Activations Density 0.031%

names and references related to individuals and their achievements

No Comments

No Known Activations