INDEX

Explanations

locations and geographic references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

alez

-0.16

ogg

-0.15

str

-0.15

ayed

-0.15

ered

-0.15

onet

-0.14

leta

-0.14

anim

-0.14

hus

-0.14

lined

-0.14

POSITIVE LOGITS

 tÃ´

0.15

SessionFactory

0.14

uso

0.14

ãģ£ãģ¡

0.14

qed

0.13

 discrepan

0.13

 Commonwealth

0.13

idy

0.13

(Cl

0.13

Activations Density 0.073%

locations and geographic references

No Comments

No Known Activations