INDEX

Explanations

references to consequences and impacts of various events or policies

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

-0.14

 ancest

-0.13

ua

-0.13

azor

-0.13

_activ

-0.13

 sklad

-0.13

 struk

-0.13

_mux

-0.13

 prest

-0.12

POSITIVE LOGITS

 effects

0.45

 Effects

0.38

effects

0.38

 impact

0.36

Effects

0.36

Impact

0.35

-effects

0.34

 impacts

0.34

 effect

0.34

impact

0.33

Activations Density 0.232%

references to consequences and impacts of various events or policies

No Comments

No Known Activations