INDEX

Explanations

connections and interactions between actions and their consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

actions

-0.15

egot

-0.15

ae

-0.14

alk

-0.14

 bolt

-0.14

ahn

-0.14

 self

-0.14

self

-0.14

 Past

-0.14

running

-0.14

POSITIVE LOGITS

ë¦¬ì¦Ī

0.14

iloc

0.14

IFT

0.14

èĨ

0.14

olina

0.14

èįĲ

0.13

ERIC

0.13

arena

0.13

Ð»Ð¾Ð±

0.13

Activations Density 0.196%

connections and interactions between actions and their consequences

No Comments

No Known Activations