INDEX

Explanations

terms related to geometric properties and spatial features in a dataset

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

mus

-0.16

hum

-0.16

linkplain

-0.16

Hum

-0.15

apon

-0.15

 inde

-0.15

dap

-0.15

 Estates

-0.15

Hum

-0.15

 indul

-0.15

POSITIVE LOGITS

ernaut

0.16

eness

0.16

ois

0.16

Bed

0.15

 Sext

0.15

 Combo

0.15

IFS

0.15

ifice

0.14

aha

0.14

asan

0.14

Activations Density 0.221%

terms related to geometric properties and spatial features in a dataset

No Comments

No Known Activations