INDEX

Explanations

technical parameters and settings related to programming or data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

late

-0.17

 late

-0.16

hq

-0.15

opoulos

-0.15

ament

-0.15

_WP

-0.15

bot

-0.15

cu

-0.15

ekl

-0.14

agua

-0.14

POSITIVE LOGITS

_macros

0.16

vetica

0.14

@student

0.14

asString

0.14

 Palest

0.14

 Palestin

0.14

_pci

0.14

raquo

0.14

iesel

0.14

.Debugger

0.13

Activations Density 0.037%

technical parameters and settings related to programming or data structures

No Comments

No Known Activations