INDEX

Explanations

specific geographic locations or regions mentioned in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

avern

-0.15

iali

-0.15

udi

-0.13

BASH

-0.13

nie

-0.13

ubbo

-0.13

 Bakan

-0.13

Ð·Ð½Ð°ÑĩÐ°

-0.13

adius

-0.13

,DB

-0.13

POSITIVE LOGITS

=<?=

0.15

<?,

0.14

onn

0.14

 Mellon

0.14

anlÄ±k

0.14

DataSetChanged

0.14

zone

0.14

cott

0.13

Mob

0.13

Activations Density 0.068%

specific geographic locations or regions mentioned in the text

No Comments

No Known Activations