INDEX

Explanations

prepositions and directional language related to location and travel

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

idden

-0.17

Ø§Ø

-0.16

.Apis

-0.16

.Toolkit

-0.15

printStats

-0.15

yat

-0.14

ãĤ¿ãĥ¼

-0.14

istar

-0.14

apia

-0.14

reau

-0.14

POSITIVE LOGITS

ihan

0.19

 Wells

0.17

gere

0.15

 Math

0.15

,exports

0.15

 Nich

0.14

 detail

0.14

è¦

0.14

va

0.14

 past

0.14

Activations Density 0.001%

prepositions and directional language related to location and travel

No Comments

No Known Activations