INDEX

Explanations

references to transitions or changes in states or conditions

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

ungi

-0.15

maker

-0.14

ustain

-0.14

lamp

-0.14

ocio

-0.14

uffy

-0.14

pair

-0.14

song

-0.14

ufact

-0.14

ÑģÐ¾ÑĢ

-0.14

POSITIVE LOGITS

brero

0.16

loth

0.15

æ¸¡

0.15

licit

0.15

tones

0.14

urette

0.14

DTD

0.14

º

0.13

Activations Density 0.013%

references to transitions or changes in states or conditions

No Comments

No Known Activations