INDEX

Explanations

specific nouns and descriptors that indicate various aspects of human experience and activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

arde

-0.18

Ã¡r

-0.15

ÑĥÑģÑĤ

-0.15

rek

-0.15

åħĥ

-0.14

ned

-0.14

andin

-0.14

 Ð¾Ð²

-0.14

edis

-0.14

orama

-0.14

POSITIVE LOGITS

ourcem

0.16

ãģ¾ãģŁãģ¯

0.14

acho

0.14

á»¡

0.14

ottom

0.14

icari

0.14

ught

0.14

 Paste

0.14

wick

0.14

Activations Density 0.004%

specific nouns and descriptors that indicate various aspects of human experience and activities

No Comments

No Known Activations