INDEX

Explanations

specific programming keywords and syntax-related terms

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

azor

-0.15

Î¯Î´

-0.15

Ki

-0.15

ogl

-0.14

Ki

-0.14

Ìģc

-0.14

 Kramer

-0.14

obi

-0.14

loo

-0.13

 Harr

-0.13

POSITIVE LOGITS

áº¾

0.15

Ð¾Ð¶Ðµ

0.15

 Traverse

0.14

ãĥĭãĤ¢

0.14

amerate

0.14

izza

0.14

ssi

0.14

outu

0.14

elerik

0.13

CKER

0.13

Activations Density 0.156%

specific programming keywords and syntax-related terms

No Comments

No Known Activations