INDEX

Explanations

references to mental health assessments and interventions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

 marg

-0.15

argin

-0.14

ex

-0.14

 camp

-0.14

tut

-0.14

antal

-0.14

opt

-0.14

ki

-0.13

 Marg

-0.13

exp

-0.13

POSITIVE LOGITS

score

0.20

 scoring

0.20

 score

0.19

 scores

0.18

 Score

0.18

 Invent

0.17

 scales

0.16

 scored

0.16

-score

0.16

SCORE

0.16

Activations Density 0.020%

references to mental health assessments and interventions

No Comments

No Known Activations

references to mental health assessments and interventions

No Comments

No Known Activations