INDEX

Explanations

names of movies, TV shows, or notable cultural productions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

eshire

-0.17

ernen

-0.16

AllWindows

-0.15

Ø·ÙĨ

-0.14

ichern

-0.13

ussen

-0.13

andise

-0.13

kup

-0.13

´Ģ

-0.13

 Blaze

-0.13

POSITIVE LOGITS

å·»

0.16

enda

0.14

okol

0.14

ego

0.14

Ø±ÛĮØ²

0.14

ÐµÑĢÐ¸Ð½Ð°

0.13

affles

0.13

ãģ¡ãĤĥãĤĵ

0.13

ê¸ī

0.13

onium

0.13

Activations Density 0.259%

names of movies, TV shows, or notable cultural productions

No Comments

No Known Activations