INDEX

Explanations

specific tokens related to URLs, links, or references to web content

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

-0.28

ERRUPT

-0.25

SM

-0.22

-0.21

SB

-0.21

SR

-0.20

eam

-0.20

POSITIVE LOGITS

enticated

0.17

sip

0.17

ãĥ³

0.17

WARN

0.16

chalk

0.15

NAL

0.15

raq

0.15

plier

0.14

enticate

0.14

ails

0.14

Activations Density 0.186%

specific tokens related to URLs, links, or references to web content

No Comments

No Known Activations