INDEX

Explanations

references to audio and listening features of headphones

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ahlen

-0.17

 headphones

-0.16

Ø§ÙĪØ±

-0.15

Footer

-0.15

emento

-0.15

uhan

-0.14

otti

-0.14

atron

-0.14

 nails

-0.14

POSITIVE LOGITS

/apt

0.21

Apt

0.20

apt

0.19

apt

0.18

 voice

0.16

EQ

0.16

 Voice

0.16

DSP

0.16

voice

0.15

 Qualcomm

0.15

Activations Density 0.026%

references to audio and listening features of headphones

No Comments

No Known Activations