INDEX

Explanations

references to specific scientific articles and their identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

agal

-0.17

io

-0.16

ono

-0.16

errat

-0.15

pong

-0.15

emin

-0.14

ulus

-0.14

aya

-0.14

itat

-0.13

POSITIVE LOGITS

 CHARSET

0.18

áºł

0.15

SetActive

0.15

ĵn

0.15

ASET

0.14

_CF

0.14

Destructor

0.13

ÐµÑĢÐ³

0.13

_regeneration

0.13

.EventHandler

0.13

Activations Density 0.012%

references to specific scientific articles and their identifiers

No Comments

No Known Activations