INDEX

Explanations

specific names or terminologies related to geographical and scientific concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

iping

-0.15

='".

-0.14

igg

-0.14

redits

-0.14

_iff

-0.14

ãĥ£

-0.14

å®ļ

-0.14

ering

-0.13

DeviceInfo

-0.13

ZO

-0.13

POSITIVE LOGITS

kir

0.20

Kir

0.19

Kir

0.18

kir

0.17

Ir

0.17

 Bris

0.15

 porr

0.15

ãĥĪãĥª

0.15

NU

0.14

Ir

0.14

Activations Density 0.057%

specific names or terminologies related to geographical and scientific concepts

No Comments

No Known Activations