INDEX

Explanations

references to scholarly works and academic publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Extension

-0.18

iren

-0.16

áº¡ng

-0.15

igan

-0.15

cel

-0.15

ÐµÑĢÐº

-0.15

Extension

-0.14

_extension

-0.14

extension

-0.14

omb

-0.14

POSITIVE LOGITS

AGER

0.16

Ral

0.15

BorderStyle

0.15

ials

0.14

LOAT

0.14

.Generated

0.14

enna

0.14

ibur

0.14

KIT

0.14

nave

0.14

Activations Density 0.017%

references to scholarly works and academic publications

No Comments

No Known Activations