INDEX

Explanations

instances of talks and presentations being scheduled or discussed

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

egration

-0.15

oord

-0.15

-ass

-0.14

 desn

-0.14

baz

-0.14

ooks

-0.14

ase

-0.14

Ass

-0.13

Creators

-0.13

elerine

-0.13

POSITIVE LOGITS

wargs

0.16

SelectedItem

0.15

ÐµÑĢÐº

0.15

.websocket

0.15

ifen

0.15

ì§¸

0.15

robat

0.14

Ø®Ø§ÙĨ

0.14

udu

0.14

poster

0.13

Activations Density 0.238%

instances of talks and presentations being scheduled or discussed

No Comments

No Known Activations