INDEX

Explanations

possessive forms indicating ownership or association

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

rang

-0.17

olan

-0.16

ello

-0.16

Yol

-0.15

ultz

-0.15

gre

-0.15

tel

-0.15

enci

-0.15

st

-0.14

gin

-0.14

POSITIVE LOGITS

'gc

0.17

wayne

0.17

.scalablytyped

0.15

ercul

0.14

ogh

0.14

_CY

0.14

orgen

0.14

.deb

0.14

ogl

0.14

MI

0.13

Activations Density 0.036%

possessive forms indicating ownership or association

No Comments

No Known Activations