INDEX

Explanations

phrases indicating recommendations or suggestions, particularly related to entertainment or media

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

vas

-0.17

IDX

-0.16

coli

-0.16

uppe

-0.15

cano

-0.15

coe

-0.15

msp

-0.15

lator

-0.15

gende

-0.14

GetMethod

-0.14

POSITIVE LOGITS

udes

0.18

illy

0.15

ahu

0.14

ammers

0.14

amm

0.14

%{

0.14

UIBarButtonItem

0.14

icios

0.14

ableView

0.14

anmar

0.13

Activations Density 0.001%

phrases indicating recommendations or suggestions, particularly related to entertainment or media

No Comments

No Known Activations