INDEX

Explanations

references to familial or relational connections in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ipple

-0.15

ulan

-0.15

rente

-0.15

ternet

-0.15

Ð¶Ð¸

-0.14

ieren

-0.14

lijah

-0.14

uali

-0.14

PRETTY

-0.14

ulg

-0.14

POSITIVE LOGITS

ale

0.17

 éł

0.16

oupon

0.14

 Listing

0.14

 Caldwell

0.14

 listing

0.14

_TA

0.13

ypo

0.13

_pars

0.13

Activations Density 0.375%

references to familial or relational connections in various contexts

No Comments

No Known Activations