INDEX

Explanations

words related to formal structures and assignments, particularly in a legal or administrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

çŃĭ

-0.16

elib

-0.16

uish

-0.16

 Harrison

-0.14

affer

-0.14

 Mercer

-0.14

ingu

-0.14

åľ³

-0.14

ÐµÐ¿

-0.14

aban

-0.14

POSITIVE LOGITS

Til

0.17

credited

0.14

ÑĭÐ²

0.14

Éµ

0.13

 tilt

0.13

 norm

0.13

Maj

0.13

Nah

0.13

indows

0.13

apol

0.13

Activations Density 0.006%

words related to formal structures and assignments, particularly in a legal or administrative context

No Comments

No Known Activations