INDEX

Explanations

proper names, particularly those of authors or individuals relevant in a narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ENTA

-0.16

Ð°ÑĨÐ¸

-0.16

omor

-0.15

invoke

-0.15

heid

-0.14

isas

-0.14

asts

-0.14

.Inv

-0.14

ouro

-0.14

Ð³Ð»Ñı

-0.14

POSITIVE LOGITS

chnitt

0.16

 Caesar

0.15

Jul

0.14

´

0.14

 Romeo

0.14

olg

0.14

 Dumpster

0.14

Ð»ÑĥÑĩ

0.13

 elementary

0.13

Jul

0.13

Activations Density 0.045%

proper names, particularly those of authors or individuals relevant in a narrative context

No Comments

No Known Activations