INDEX

Explanations

numerical values and indicators related to data or statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ional

-0.18

phony

-0.15

qli

-0.15

DL

-0.14

reator

-0.14

Äįel

-0.14

owe

-0.13

Dark

-0.13

acket

-0.13

ogle

-0.13

POSITIVE LOGITS

uti

0.16

ssi

0.15

URLRequest

0.15

ked

0.15

kok

0.14

_Render

0.14

vana

0.14

Ã´te

0.14

ote

0.14

imore

0.13

Activations Density 0.017%

numerical values and indicators related to data or statistics

No Comments

No Known Activations