INDEX

Explanations

problem-solving and troubleshooting dialogues

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

iasi

-0.17

trs

-0.16

ContentAlignment

-0.16

asti

-0.16

uno

-0.14

otal

-0.14

Insets

-0.14

ezi

-0.14

Compat

-0.13

erken

-0.13

POSITIVE LOGITS

icana

0.20

rien

0.17

ylon

0.16

riel

0.14

rie

0.14

Ð´Ð°Ñħ

0.14

DH

0.14

 Woodward

0.13

ido

0.13

ema

0.13

Activations Density 0.029%

problem-solving and troubleshooting dialogues

No Comments

No Known Activations