INDEX

Explanations

numeric values and alphanumeric codes

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

oose

-0.15

iera

-0.15

Äĥr

-0.15

Random

-0.14

tel

-0.14

itel

-0.14

prak

-0.14

 lead

-0.14

enemy

-0.14

rms

-0.14

POSITIVE LOGITS

ksi

0.17

iaux

0.17

ofday

0.16

elden

0.16

contres

0.15

 prostituer

0.15

 diseÃ±ador

0.15

ÏĥÎ¹Î±

0.15

 actionTypes

0.14

pon

0.14

Activations Density 0.021%

numeric values and alphanumeric codes

No Comments

No Known Activations