INDEX

Explanations

references to third-party interactions and privacy policies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ones

-0.17

hra

-0.16

raz

-0.15

 å¯

-0.15

 Stark

-0.15

idden

-0.15

igen

-0.14

udge

-0.14

aja

-0.14

urch

-0.14

POSITIVE LOGITS

 independently

0.20

 independent

0.20

 independ

0.17

 Independent

0.17

 elsewhere

0.17

çĭ¬ç«ĭ

0.16

Independent

0.16

abbo

0.16

 separate

0.16

iani

0.15

Activations Density 0.092%

references to third-party interactions and privacy policies

No Comments

No Known Activations