INDEX

Explanations

mentions of "paper" in various contexts

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

spark

-0.19

scient

-0.16

sin

-0.16

say

-0.15

ĽĪ

-0.15

ship

-0.15

yk

-0.15

serter

-0.15

ote

-0.15

otu

-0.15

POSITIVE LOGITS

clip

0.33

backs

0.26

-paper

0.25

doll

0.23

trail

0.23

.li

0.21

 Paper

0.21

board

0.21

 towel

0.20

.paper

0.20

Activations Density 0.028%

mentions of "paper" in various contexts

No Comments

No Known Activations

mentions of "paper" in various contexts

No Comments

No Known Activations