INDEX

Explanations

instances of listening or hearing in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

æĮ¯ãĤĬ

-0.15

åĪĬ

-0.14

ãģĤãģĴ

-0.14

ÙĪØ´

-0.14

ogl

-0.14

_Action

-0.14

 visible

-0.14

 viewers

-0.13

agram

-0.13

 Pics

-0.13

POSITIVE LOGITS

 voices

0.21

/watch

0.20

audio

0.19

 audio

0.19

 heartbeat

0.19

 podcasts

0.19

 footsteps

0.18

 crunch

0.18

 conversation

0.17

 sounds

0.17

Activations Density 0.074%

instances of listening or hearing in various contexts

No Comments

No Known Activations