INDEX

Explanations

possessive pronouns, specifically variations of "my"

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

ibu

-0.16

 blame

-0.14

mne

-0.14

ÑĤÑĭ

-0.14

pesan

-0.14

.gg

-0.14

istle

-0.14

 æ¾

-0.14

fm

-0.13

edi

-0.13

POSITIVE LOGITS

own

0.20

/her

0.16

opia

0.16

_own

0.15

SELF

0.15

own

0.15

rtle

0.14

Own

0.14

ugin

0.14

AMB

0.13

Activations Density 0.094%

possessive pronouns, specifically variations of "my"

No Comments

No Known Activations