INDEX

Explanations

actions and states related to readiness or preparation

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

anko

-0.17

 Rage

-0.16

ruh

-0.15

ķĮ

-0.14

ounded

-0.14

rides

-0.14

Affected

-0.14

ogan

-0.13

ambi

-0.13

 gratuits

-0.13

POSITIVE LOGITS

 ready

1.03

 Ready

0.85

ready

0.84

 READY

0.82

Ready

0.77

-ready

0.74

_ready

0.71

.ready

0.67

READY

0.67

 readiness

0.66

Activations Density 0.154%

actions and states related to readiness or preparation

No Comments

No Known Activations