INDEX

Explanations

references to programming code elements and related attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

oe

-0.17

 Whites

-0.16

oler

-0.16

ente

-0.15

.getID

-0.15

çĶ²

-0.15

tar

-0.14

stood

-0.14

åĽ½

-0.14

Tables

-0.13

POSITIVE LOGITS

 cref

0.31

acas

0.16

/fw

0.15

andin

0.15

paramref

0.15

 Gins

0.14

ynth

0.14

azer

0.14

.unsplash

0.14

asca

0.14

Activations Density 0.002%

references to programming code elements and related attributes

No Comments

No Known Activations