INDEX

Explanations

terms related to stability and instability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

yb

-0.16

etre

-0.15

ivity

-0.15

ous

-0.15

pell

-0.15

ETERS

-0.15

 Pais

-0.15

owan

-0.14

eren

-0.14

fulness

-0.14

POSITIVE LOGITS

 stability

0.20

mate

0.20

coins

0.20

 unstable

0.20

mates

0.19

 Stability

0.19

ilty

0.18

coin

0.18

 instability

0.18

stable

0.18

Activations Density 0.026%

terms related to stability and instability

No Comments

No Known Activations