INDEX

Explanations

statements asserting truth or validity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

lander

-0.17

ker

-0.14

tet

-0.14

urch

-0.14

 Mattis

-0.14

Sno

-0.14

¸ı

-0.14

-0.13

ancias

-0.13

rom

-0.13

POSITIVE LOGITS

ÑĨÐµÐ½

0.15

OTES

0.15

TestData

0.15

mpp

0.14

angl

0.14

caler

0.14

ikat

0.14

chw

0.13

sgi

0.13

chn

0.13

Activations Density 0.029%

statements asserting truth or validity

No Comments

No Known Activations