INDEX

Explanations

references to environmental pollutants and health-related hazards

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

_chunks

-0.15

xml

-0.15

neau

-0.14

estroy

-0.14

esor

-0.14

ceipt

-0.13

Ã¡ndez

-0.13

ishop

-0.13

ctxt

-0.13

ï»¿↵↵

-0.13

POSITIVE LOGITS

adows

0.16

oline

0.15

izzas

0.15

iol

0.15

IPA

0.15

emann

0.14

Ø²ÛĮ

0.13

 card

0.13

ibling

0.13

Activations Density 0.002%

references to environmental pollutants and health-related hazards

No Comments

No Known Activations