INDEX

Explanations

references to "Tor," indicating a focus on topics related to the Tor network or its developments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ovic

-0.17

exter

-0.15

æĶ

-0.15

enh

-0.15

ema

-0.15

ouri

-0.15

tas

-0.14

vyt

-0.14

eea

-0.14

ĩ

-0.14

POSITIVE LOGITS

stan

0.16

EPS

0.15

ignal

0.15

paque

0.15

blem

0.15

beck

0.15

åĶ

0.14

izons

0.14

oulouse

0.14

otton

0.14

Activations Density 0.011%

references to "Tor," indicating a focus on topics related to the Tor network or its developments

No Comments

No Known Activations