INDEX

Explanations

programming-related terminology and structures in code snippets

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

itter

-0.18

aji

-0.18

ITTER

-0.16

efore

-0.15

ouri

-0.15

olas

-0.14

raya

-0.14

 Hlav

-0.14

aho

-0.14

endon

-0.14

POSITIVE LOGITS

 hood

0.17

0.16

ship

0.16

 Ethi

0.15

Ã¡cil

0.15

 Hood

0.14

:::

0.14

Activations Density 0.190%

programming-related terminology and structures in code snippets

No Comments

No Known Activations