INDEX

Explanations

adjectives that describe feelings 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 @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

Äĥr

-0.16

istar

-0.15

eing

-0.14

eldig

-0.14

anio

-0.14

,—

-0.14

ouver

-0.14

addtogroup

-0.14

thern

-0.13

ollar

-0.13

POSITIVE LOGITS

0.16

 Walsh

0.15

á»Ļi

0.15

–

0.14

’Brien

0.14

0.13

via

0.13

 tang

0.13

Activations Density 0.000%

adjectives that describe feelings or conditions

No Comments

No Known Activations