INDEX

Explanations

items related to safety and protective gear

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

pent

-0.17

SED

-0.17

ixer

-0.15

ushman

-0.15

à¥įà¤Łà¤®

-0.14

IXEL

-0.14

ocking

-0.14

agas

-0.14

 cháº£y

-0.14

uitka

-0.14

POSITIVE LOGITS

 protect

0.16

Bib

0.16

 worn

0.16

-mount

0.15

 layers

0.15

ombat

0.14

 protects

0.14

inke

0.14

protect

0.14

.shtml

0.14

Activations Density 0.076%

items related to safety and protective gear

No Comments

No Known Activations