INDEX

Explanations

contact information and details for services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

éĥİ

-0.15

abal

-0.15

angs

-0.14

×ª

-0.14

anki

-0.14

Ð¾ÑĢÐ°Ð·

-0.14

trap

-0.14

ft

-0.14

 Dost

-0.13

alive

-0.13

POSITIVE LOGITS

ssc

0.15

aphore

0.15

Ð°Ð»Ð¾Ð¼

0.15

PLEX

0.14

umbledore

0.14

LF

0.14

-Am

0.14

oric

0.13

uator

0.13

Activations Density 0.046%

contact information and details for services

No Comments

No Known Activations