INDEX

Explanations

personal pronouns and expressions of personal experience or opinion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

uter

-0.15

 Presence

-0.14

oods

-0.14

iasco

-0.14

iae

-0.14

 skup

-0.14

utta

-0.14

rise

-0.13

 Toll

-0.13

//~

-0.13

POSITIVE LOGITS

 frequently

0.23

 often

0.18

oft

0.18

 encounter

0.17

 encounters

0.17

 witness

0.16

 personally

0.16

 commonly

0.15

 increasingly

0.15

 firm

0.15

Activations Density 0.130%

personal pronouns and expressions of personal experience or opinion

No Comments

No Known Activations