INDEX

Explanations

symbols or patterns related to hierarchical classification or organization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

uche

-0.16

jab

-0.15

zig

-0.15

aternity

-0.15

lehem

-0.14

Ø¡

-0.14

ozor

-0.14

Ð²Ð¸Ñī

-0.14

quina

-0.14

lander

-0.14

POSITIVE LOGITS

 nowhere

0.17

-overlay

0.15

nel

0.14

 whom

0.14

uÅŁ

0.14

uÃ©

0.14

me

0.14

 Ø£Ø¬ÙĦ

0.14

Dut

0.13

idad

0.13

Activations Density 0.032%

symbols or patterns related to hierarchical classification or organization

No Comments

No Known Activations