INDEX

Explanations

representations of sounds and their descriptions in the environment

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

 hear

-0.20

apiro

-0.17

 hearing

-0.17

 Hearth

-0.15

pes

-0.15

ekim

-0.15

imon

-0.14

POSITIVE LOGITS

 throat

0.17

 nasal

0.17

gut

0.15

 calls

0.15

.call

0.15

 serie

0.15

chip

0.15

-cache

0.15

IMIT

0.15

 call

0.15

Activations Density 0.019%

representations of sounds and their descriptions in the environment

No Comments

No Known Activations