INDEX

Explanations

words related to significant individuals or entities, possibly indicating a focus on relationships or character connections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

oy

-0.16

ynth

-0.15

undi

-0.14

à¸·à¸Ńà¸Ĥ

-0.14

pagination

-0.14

inue

-0.13

ery

-0.13

oyer

-0.13

altung

-0.13

ccione

-0.13

POSITIVE LOGITS

utto

0.16

à¤¦à¤°

0.15

.um

0.15

nech

0.15

alu

0.14

Lid

0.14

é£Ł

0.14

.ribbon

0.14

aeda

0.14

ones

0.13

Activations Density 0.002%

words related to significant individuals or entities, possibly indicating a focus on relationships or character connections

No Comments

No Known Activations