INDEX

Explanations

specific social media tags and handles related to sports or public figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

echan

-0.19

Ã³m

-0.18

plib

-0.16

eding

-0.15

 poloÅ¾

-0.14

rored

-0.14

rowned

-0.14

etta

-0.14

trap

-0.13

owan

-0.13

POSITIVE LOGITS

pic

0.23

pic

0.16

coe

0.15

(pic

0.15

-pic

0.15

ÑĢÐ´

0.14

ance

0.14

bsub

0.14

ByExample

0.14

 Sund

0.14

Activations Density 0.005%

specific social media tags and handles related to sports or public figures

No Comments

No Known Activations