INDEX

Explanations

terms related to programming languages and software functionalities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 constr

-0.18

 recre

-0.17

 under

-0.17

 conj

-0.17

 demonstr

-0.16

 thru

-0.16

 analy

-0.15

obs

-0.15

exp

-0.15

POSITIVE LOGITS

Ã¬

0.19

 lung

0.19

zione

0.18

azione

0.18

Ã²

0.17

ÅĤe

0.17

izione

0.17

 rifles

0.17

azioni

0.16

 tale

0.16

Activations Density 0.186%

terms related to programming languages and software functionalities

No Comments

No Known Activations