INDEX

Explanations

terms related to health metrics and assessments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

adena

-0.18

abbit

-0.18

aden

-0.17

.ActionBar

-0.17

ABI

-0.17

adic

-0.16

.Ab

-0.16

abies

-0.16

abb

-0.16

ador

-0.16

POSITIVE LOGITS

0.17

 ihnen

0.17

Ay

0.16

 them

0.16

ayd

0.16

bbw

0.16

auss

0.16

them

0.16

Beta

0.16

Baz

0.15

Activations Density 0.070%

terms related to health metrics and assessments

No Comments

No Known Activations