INDEX

Explanations

conversational phrases and expressions indicating thought and inquiry

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

anford

-0.16

atte

-0.15

 Messaging

-0.15

 Milli

-0.14

MimeType

-0.14

Mari

-0.14

æµª

-0.14

Marsh

-0.14

 molding

-0.14

/msg

-0.14

POSITIVE LOGITS

 mean

0.98

 means

0.85

 Mean

0.81

mean

0.81

Mean

0.74

 meant

0.73

means

0.72

 Means

0.70

_mean

0.68

-mean

0.68

Activations Density 0.268%

conversational phrases and expressions indicating thought and inquiry

No Comments

No Known Activations