INDEX

Explanations

words related to reciprocal actions or relationships

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

anja

-0.15

adden

-0.15

orman

-0.15

loquent

-0.14

atura

-0.14

Î¾Î¹

-0.14

cken

-0.14

 Hats

-0.14

ets

-0.13

 sÃ¼t

-0.13

POSITIVE LOGITS

icode

0.17

ood

0.16

enor

0.15

 Athe

0.15

enan

0.14

thermal

0.14

ÙħØ§ÙĦ

0.14

 anon

0.14

ipers

0.14

Activations Density 0.001%

words related to reciprocal actions or relationships

No Comments

No Known Activations