INDEX

Explanations

programming-related keywords and functions

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

 Abram

-0.15

 sleeve

-0.14

 Prompt

-0.14

-0.13

.synthetic

-0.13

ThreadPool

-0.13

 slova

-0.13

æ¯Ľ

-0.13

ÑĥÑĩÐ°

-0.13

outine

-0.13

POSITIVE LOGITS

 JSON

0.60

 json

0.58

JSON

0.55

json

0.54

.json

0.51

_json

0.50

 Json

0.50

_JSON

0.50

-json

0.49

.JSON

0.48

Activations Density 0.211%

programming-related keywords and functions

No Comments

No Known Activations