INDEX

Explanations

references to legal documents and procedural contexts

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

izza

-0.15

odor

-0.14

 LiÃªn

-0.14

ARI

-0.14

orden

-0.14

-0.13

azz

-0.13

ogan

-0.13

orch

-0.13

POSITIVE LOGITS

arget

0.18

Ð¾Ð¾Ð±ÑĢÐ°Ð·

0.16

iens

0.16

imals

0.15

igne

0.15

ibel

0.14

 bracket

0.14

 Bates

0.14

áº¡

0.14

inclusive

0.14

Activations Density 0.099%

references to legal documents and procedural contexts

No Comments

No Known Activations