INDEX

Explanations

patterns related to numerical values and timestamps

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

reator

-0.18

trys

-0.16

avras

-0.15

 Redistributions

-0.15

 Blitz

-0.15

validator

-0.14

quan

-0.14

eriod

-0.14

itmap

-0.14

licht

-0.14

POSITIVE LOGITS

ure

0.16

 wire

0.15

arn

0.15

ware

0.14

yal

0.14

 gist

0.14

IMA

0.14

part

0.14

ama

0.13

 Spike

0.13

Activations Density 0.194%

patterns related to numerical values and timestamps

No Comments

No Known Activations