INDEX

Explanations

technical terms and code-related elements in programming language contexts

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

isse

-0.14

 Bing

-0.14

Î¯Î½Î·

-0.14

Ŀ

-0.13

uchen

-0.13

é«

-0.13

kus

-0.13

,{"

-0.13

POSITIVE LOGITS

cej

0.16

oshi

0.15

asco

0.15

 KÄ±r

0.15

itm

0.14

ervals

0.14

adm

0.14

.dds

0.13

.py

0.13

osc

0.13

Activations Density 0.035%

technical terms and code-related elements in programming language contexts

No Comments

No Known Activations