INDEX

Explanations

words and phrases related to immediate or recent states and conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ppe

-0.16

isContained

-0.15

lier

-0.14

zie

-0.14

.yang

-0.14

opia

-0.14

 Voll

-0.13

Ð°Ð½Ð¸ÑĨ

-0.13

lay

-0.13

pped

-0.13

POSITIVE LOGITS

-success

0.18

-empty

0.17

-inf

0.16

 very

0.16

da

0.16

-too

0.16

-ob

0.15

-icon

0.15

-existing

0.15

-cancel

0.15

Activations Density 0.099%

words and phrases related to immediate or recent states and conditions

No Comments

No Known Activations