INDEX

Explanations

references to legislative bills or governmental proposals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

 Robbins

-0.15

inder

-0.15

Ä

-0.14

apa

-0.14

ville

-0.13

 Frost

-0.13

 conversion

-0.13

ÑĥÑĢÑĭ

-0.13

 Goodman

-0.13

oe

-0.13

POSITIVE LOGITS

eyse

0.14

gles

0.14

reich

0.14

Æ°á»£t

0.13

erdings

0.13

amer

0.13

Lifetime

0.13

à¥ģà¤¹

0.13

Balancer

0.13

kinci

0.13

Activations Density 0.030%

references to legislative bills or governmental proposals

No Comments

No Known Activations