INDEX

Explanations

programming-related terms and functions

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

raid

-0.17

agy

-0.14

Ordinal

-0.14

Gallery

-0.13

wand

-0.13

.Reporting

-0.13

.Batch

-0.13

CCD

-0.13

 Bowman

-0.13

 reco

-0.13

POSITIVE LOGITS

0.20

 sustain

0.20

 envelopes

0.20

 sound

0.19

 envelope

0.19

Envelope

0.18

 Audio

0.18

gain

0.18

 audio

0.17

éŁ³

0.17

Activations Density 0.009%

programming-related terms and functions

No Comments

No Known Activations