INDEX

Explanations

common words or phrases related to health and well-being contexts

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

ansen

-0.16

tif

-0.16

none

-0.15

gate

-0.15

OfType

-0.14

itchens

-0.14

æĳĨ

-0.14

ÙĦÙī

-0.14

gel

-0.14

SCRI

-0.13

POSITIVE LOGITS

uran

0.16

0.15

issen

0.15

0.14

 Ð¿ÑĢÐ¾

0.14

oras

0.14

vyk

0.14

Kro

0.14

/spec

0.13

lein

0.13

Activations Density 0.001%

common words or phrases related to health and well-being contexts

No Comments

No Known Activations