INDEX

Explanations

technical terms and elements related to coding and programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

iro

-0.18

åħ·

-0.15

anie

-0.14

awah

-0.14

Ð½Ð¸ÑĨ

-0.14

âĢ¦âĢ¦ãĢĤ

-0.14

Ð°Ð½Ð¸ÑĨ

-0.14

ÑĩÐ¸Ð¹

-0.14

 åŁ

-0.14

enders

-0.13

POSITIVE LOGITS

ento

0.15

_kw

0.14

 devast

0.14

UNDLE

0.14

ìĭ¬

0.14

CLUD

0.14

Activations Density 0.085%

technical terms and elements related to coding and programming

No Comments

No Known Activations