INDEX

Explanations

code snippets and programming constructs within Python context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

agini

-0.18

ytt

-0.14

cci

-0.14

phyl

-0.14

zew

-0.14

 æł¼

-0.14

Uuid

-0.14

.ce

-0.14

Bon

-0.14

quier

-0.14

POSITIVE LOGITS

cop

0.18

.backends

0.15

 Silence

0.15

IGNED

0.14

ÏģÎº

0.14

ehr

0.14

cop

0.14

 silence

0.14

 mutually

0.13

olist

0.13

Activations Density 0.178%

code snippets and programming constructs within Python context

No Comments

No Known Activations