INDEX

Explanations

references to nobility or titles

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

mtree

-0.15

boa

-0.15

=edge

-0.14

Creators

-0.14

adh

-0.14

Disk

-0.14

à¸Ĺà¸Ńà¸ĩ

-0.14

umnos

-0.13

inker

-0.13

erior

-0.13

POSITIVE LOGITS

 Appe

0.16

rette

0.15

bing

0.15

á»įng

0.15

 conf

0.14

ilst

0.14

per

0.14

ega

0.14

ire

0.14

Activations Density 0.003%

references to nobility or titles

No Comments

No Known Activations