INDEX

Explanations

references to the extent or range of projects or activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

ernals

-0.17

iser

-0.17

abeth

-0.17

ms

-0.16

nbsp

-0.16

iona

-0.15

ians

-0.15

ernal

-0.15

 penny

-0.15

lad

-0.15

POSITIVE LOGITS

less

0.19

OfWork

0.19

andin

0.18

olla

0.16

egasus

0.15

enef

0.15

yw

0.14

'nun

0.14

ertino

0.14

 narrow

0.14

Activations Density 0.014%

references to the extent or range of projects or activities

No Comments

No Known Activations