INDEX

Explanations

data and descriptions related to scientific research or findings

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

 Salmon

-0.16

inct

-0.15

à¤Ĥà¤¶

-0.15

 mixed

-0.14

orca

-0.14

å¿Ĺ

-0.14

inka

-0.14

oro

-0.14

enz

-0.13

xcf

-0.13

POSITIVE LOGITS

herits

0.16

 ÑĤÐ¾Ð»

0.15

Éµ

0.15

uchs

0.15

mil

0.15

avit

0.14

apore

0.14

Mil

0.14

HORT

0.14

ogo

0.14

Activations Density 0.063%

data and descriptions related to scientific research or findings

No Comments

No Known Activations