INDEX

Explanations

programming-related keywords and errors

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

-0.18

-0.15

icle

-0.14

endoza

-0.14

 Agenda

-0.14

POSITIVE LOGITS

Unmarshaller

0.18

±Ð¾ÑĤ

0.15

linkplain

0.14

edo

0.14

è¾°

0.14

__;

0.14

IPH

0.14

readcr

0.14

íħľ

0.14

udit

0.13

Activations Density 0.005%

programming-related keywords and errors

No Comments

No Known Activations