INDEX

Explanations

various names, possibly of people or organizations, along with certain numerical identifiers and dates

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

usch

-0.15

odon

-0.15

roj

-0.14

rome

-0.14

.selector

-0.14

inki

-0.14

competition

-0.13

 ÑĶÐ²

-0.13

assador

-0.13

meet

-0.13

POSITIVE LOGITS

 femin

0.16

 junior

0.16

 senior

0.15

eon

0.15

 among

0.15

Ã¼zel

0.14

 twice

0.14

Esp

0.14

enic

0.14

aeda

0.14

Activations Density 0.041%

various names, possibly of people or organizations, along with certain numerical identifiers and dates

No Comments

No Known Activations