INDEX

Explanations

instances of the word "posted" or similar actions indicating sharing or publication

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

inet

-0.15

edBy

-0.15

osaur

-0.14

 Kick

-0.14

ç´

-0.14

 ÑĸÐ¼ÐµÐ½Ñĸ

-0.14

 factorial

-0.13

ï»¿using

-0.13

mitt

-0.13

 relie

-0.13

POSITIVE LOGITS

dif

0.14

DMA

0.14

embros

0.14

efon

0.14

aney

0.14

afort

0.13

createElement

0.13

Äįem

0.13

æĺŃ

0.13

åģ

0.13

Activations Density 0.005%

instances of the word "posted" or similar actions indicating sharing or publication

No Comments

No Known Activations