INDEX

Explanations

key actions or transformations within narrative or procedural contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

/../

-0.15

 Heap

-0.15

ctxt

-0.15

chod

-0.14

elian

-0.14

lej

-0.13

niest

-0.13

.Enqueue

-0.13

 interven

-0.13

Ð±Ð¾Ð²

-0.13

POSITIVE LOGITS

isce

0.34

iona

0.28

inge

0.27

ende

0.26

ifica

0.26

iene

0.25

ponde

0.25

segue

0.24

nde

0.24

forma

0.24

Activations Density 0.020%

key actions or transformations within narrative or procedural contexts

No Comments

No Known Activations