INDEX

Explanations

specific names or identifiers associated with individuals or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

inya

-0.17

leÅ¾it

-0.16

apt

-0.16

fat

-0.15

_shortcode

-0.15

urally

-0.15

æıĲ

-0.15

 Trou

-0.15

obody

-0.14

holds

-0.14

POSITIVE LOGITS

(DE

0.18

oyer

0.17

adero

0.15

ansa

0.15

yll

0.15

dent

0.15

/Register

0.14

uman

0.14

@protocol

0.14

Laf

0.14

Activations Density 0.089%

specific names or identifiers associated with individuals or entities

No Comments

No Known Activations