INDEX

Explanations

references to family structure and size in the context of community and support

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

(<

-0.15

apid

-0.14

 negligible

-0.13

//{{

-0.13

 Minimal

-0.13

quam

-0.13

bote

-0.12

Å©i

-0.12

Minimal

-0.12

 nues

-0.12

POSITIVE LOGITS

 large

0.85

 larger

0.85

large

0.76

 Larger

0.76

 bigger

0.70

 Large

0.70

 LARGE

0.69

Large

0.69

-large

0.67

 largest

0.65

Activations Density 0.525%

references to family structure and size in the context of community and support

No Comments

No Known Activations