INDEX

Explanations

words related to time and sequencing events

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

 excess

-0.15

Lux

-0.15

artz

-0.15

 Irvine

-0.15

smith

-0.14

places

-0.14

udur

-0.14

astes

-0.14

 Kling

-0.14

ndon

-0.14

POSITIVE LOGITS

IOR

0.16

azen

0.15

ior

0.15

quare

0.15

roc

0.15

abytes

0.14

ROC

0.14

 Hanging

0.14

reamble

0.14

ipc

0.14

Activations Density 0.006%

words related to time and sequencing events

No Comments

No Known Activations