INDEX

Explanations

specific attributes or characteristics related to various subjects or contexts

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

zin

-0.14

ika

-0.14

alleries

-0.13

Decor

-0.13

rad

-0.13

isa

-0.13

 Federation

-0.13

hua

-0.12

POSITIVE LOGITS

-regexp

0.15

bservice

0.14

utsch

0.14

rawn

0.14

iÃ§

0.14

Ð³Ð¾ÑĤÐ¾Ð²

0.14

apps

0.14

.Toolkit

0.14

heim

0.13

Ø§ÙĬÙĨ

0.13

Activations Density 0.109%

specific attributes or characteristics related to various subjects or contexts

No Comments

No Known Activations