INDEX

Explanations

phrases related to the impact of actions and consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

MethodInfo

-0.15

%C

-0.14

 Anchor

-0.14

Con

-0.14

hed

-0.13

Cot

-0.13

vinc

-0.13

anc

-0.13

POSITIVE LOGITS

iro

0.17

 Cunningham

0.14

aban

0.14

stva

0.14

olland

0.14

ses

0.14

LOCKS

0.14

IIIK

0.13

abr

0.13

-alist

0.13

Activations Density 0.241%

phrases related to the impact of actions and consequences

No Comments

No Known Activations