INDEX

Explanations

proper nouns, specifically names of characters and notable figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

/kubernetes

-0.16

RYPT

-0.15

ãĤ¿ãĥ¼

-0.15

ialis

-0.15

antis

-0.14

Æł

-0.14

çĻ

-0.14

Î¹Î²

-0.13

 Ð¿Ð¾Ð´Ñģ

-0.13

POSITIVE LOGITS

ÑĦÐ¸

0.14

 ÐłÐ¾Ð´

0.14

alle

0.14

RHS

0.14

.dup

0.14

ead

0.13

nad

0.13

ãĥ«ãĥī

0.13

KM

0.13

uang

0.13

Activations Density 0.205%

proper nouns, specifically names of characters and notable figures

No Comments

No Known Activations