INDEX

Explanations

references to notable individuals and their formal titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

erval

-0.15

iros

-0.15

iri

-0.15

alli

-0.15

abis

-0.15

rew

-0.15

iris

-0.14

ÑĢÑıÐ´Ñĥ

-0.14

velt

-0.14

hra

-0.14

POSITIVE LOGITS

_firestore

0.17

pas

0.15

inclu

0.14

 Rubio

0.14

chten

0.14

agma

0.14

iyon

0.14

 trÃ¹ng

0.14

pler

0.13

 Terminal

0.13

Activations Density 0.002%

references to notable individuals and their formal titles

No Comments

No Known Activations