INDEX

Explanations

proper nouns and names associated with individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

sandbox

-0.16

PRECATED

-0.15

ordova

-0.15

alez

-0.14

 Scoped

-0.14

Į¨

-0.14

dot

-0.14

 Ø±Ø²

-0.14

kees

-0.14

orrent

-0.13

POSITIVE LOGITS

ledo

0.17

neys

0.17

backs

0.17

 Seks

0.15

bes

0.15

lessly

0.15

onomies

0.15

Î³Î½Ïī

0.14

 accidental

0.14

Activations Density 1.343%

proper nouns and names associated with individuals

No Comments

No Known Activations