INDEX

Explanations

references to specific locations and institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

Kansas

-0.32

 Kansas

-0.32

 Missouri

-0.24

 Wichita

-0.23

 Omaha

-0.23

 Nebraska

-0.20

 Moines

-0.20

 Iowa

-0.20

Ãºn

-0.18

 Sioux

-0.18

POSITIVE LOGITS

 Tobias

0.17

 Norton

0.15

jet

0.15

Han

0.15

 Hold

0.14

Tek

0.14

Wa

0.14

èĳī

0.14

 Scotia

0.14

holm

0.14

Activations Density 0.010%

references to specific locations and institutions

No Comments

No Known Activations