INDEX

Explanations

specific details and statistics related to events and observations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

stad

-0.16

oÅ¾

-0.15

usiness

-0.15

-0.14

.habbo

-0.14

roperty

-0.14

 systematic

-0.14

enever

-0.14

actionDate

-0.13

POSITIVE LOGITS

anch

0.16

ingo

0.14

cul

0.14

_RING

0.14

arth

0.14

ãĥĥãĥĪ

0.14

ned

0.14

GIS

0.14

isode

0.14

 Auditor

0.14

Activations Density 0.102%

specific details and statistics related to events and observations

No Comments

No Known Activations