INDEX

Explanations

pronouns and their associated verbs, indicating actions and states related to various subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

NEY

-0.14

é¸

-0.13

ëĮĢ

-0.13

çĭĲ

-0.13

kills

-0.13

ulis

-0.13

_Api

-0.13

.pan

-0.13

ucker

-0.13

":"/

-0.13

POSITIVE LOGITS

oller

0.16

swire

0.15

ath

0.15

PCA

0.14

cla

0.14

enge

0.14

sworth

0.14

_OCC

0.14

enos

0.14

Activations Density 0.109%

pronouns and their associated verbs, indicating actions and states related to various subjects

No Comments

No Known Activations