INDEX

Explanations

terms related to logical systems and causal relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

prung

-0.15

vos

-0.15

 faker

-0.14

_estimator

-0.14

igr

-0.14

Tx

-0.13

 desp

-0.13

fcn

-0.13

.descriptor

-0.13

ç±

-0.13

POSITIVE LOGITS

 Curry

0.18

 Horn

0.16

 Gent

0.16

 Morav

0.15

Qed

0.15

 McCarthy

0.15

 GÃ¶

0.15

strand

0.15

 forall

0.14

.xtext

0.14

Activations Density 0.149%

terms related to logical systems and causal relationships

No Comments

No Known Activations