INDEX

Explanations

programming-related syntax and keywords

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

 Mines

-0.14

iais

-0.14

.impl

-0.14

dep

-0.14

loc

-0.13

,D

-0.13

 vaguely

-0.13

Mgr

-0.13

å¼ĺ

-0.13

odem

-0.13

POSITIVE LOGITS

uhan

0.15

okol

0.14

CKER

0.14

Ø§ÙĪØ±ÛĮ

0.14

imin

0.14

 Barnett

0.14

æ¬²

0.14

atham

0.14

ipsis

0.14

Activations Density 0.063%

programming-related syntax and keywords

No Comments

No Known Activations