INDEX

Explanations

references to individuals and their roles or relationships within specific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ambi

-0.19

podob

-0.16

alice

-0.16

ollower

-0.15

Ã¨o

-0.15

igh

-0.14

à¥°

-0.14

isel

-0.14

akra

-0.14

klÃ¤

-0.14

POSITIVE LOGITS

du

0.17

 Jones

0.16

du

0.14

0.13

hem

0.13

Fus

0.13

ãĥ³ãĤ°

0.13

greSQL

0.13

 ØªÙĤØ¯

0.13

Activations Density 0.044%

references to individuals and their roles or relationships within specific contexts

No Comments

No Known Activations