INDEX

Explanations

references to platforms or documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

uka

-0.18

Behaviour

-0.16

ural

-0.15

illo

-0.14

 Visibility

-0.13

 behavioural

-0.13

nal

-0.13

æ¥Ń

-0.13

ean

-0.13

ivel

-0.13

POSITIVE LOGITS

 persons

0.18

persons

0.17

Persons

0.16

aura

0.15

 personnes

0.15

ederland

0.15

asje

0.15

 rencont

0.15

member

0.14

plusplus

0.14

Activations Density 0.000%

references to platforms or documents

No Comments

No Known Activations