INDEX

Explanations

characteristics and descriptions related to hair or sheep features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 triangle

-0.20

 Triangle

-0.19

 triangular

-0.18

 cube

-0.18

Triangle

-0.17

 squares

-0.16

 square

-0.16

square

-0.16

 triangles

-0.16

 rectangular

-0.15

POSITIVE LOGITS

hel

0.41

 curve

0.36

 curves

0.34

-cur

0.34

 Curve

0.34

curve

0.33

hel

0.33

 spir

0.33

 spiral

0.31

Curve

0.31

Activations Density 0.115%

characteristics and descriptions related to hair or sheep features

No Comments

No Known Activations