INDEX

Explanations

names and titles associated with historical figures and places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ÑĢÑĥÐ·

-0.15

kus

-0.14

egan

-0.14

buch

-0.14

rous

-0.14

eway

-0.14

ipeg

-0.14

è½®

-0.14

phe

-0.13

Dup

-0.13

POSITIVE LOGITS

Ø³Ø¯

0.15

 Rabbit

0.14

 Rafael

0.14

 Daly

0.14

avian

0.14

cul

0.14

Ð¾Ð¿ÑĢÐ¾Ñģ

0.13

ãĥĪãĥª

0.13

 stun

0.13

BOOST

0.13

Activations Density 0.030%

names and titles associated with historical figures and places

No Comments

No Known Activations