INDEX

Explanations

interactive prompts and activities targeting children's language skills

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 è©ķä¾¡

-0.18

 FUCK

-0.17

 fucking

-0.17

 fucked

-0.17

 fucks

-0.16

Fuck

-0.16

 hell

-0.16

Ãły

-0.15

 cazzo

-0.15

 fuck

-0.15

POSITIVE LOGITS

umpt

0.19

 lots

0.19

 grown

0.17

opsy

0.16

 mommy

0.16

 Lots

0.15

 humans

0.15

lots

0.15

upil

0.15

 silly

0.15

Activations Density 0.267%

interactive prompts and activities targeting children's language skills

No Comments

No Known Activations