INDEX

Explanations

terms related to trauma and its effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

rop

-0.15

arden

-0.15

yi

-0.15

ariat

-0.15

aru

-0.14

rox

-0.14

ropy

-0.14

ovie

-0.14

Ä±klÄ±

-0.14

chia

-0.14

POSITIVE LOGITS

uma

0.40

umatic

0.39

umas

0.35

umat

0.33

jectory

0.33

jectories

0.31

pez

0.27

ipse

0.26

itors

0.25

eger

0.24

Activations Density 0.006%

terms related to trauma and its effects

No Comments

No Known Activations