INDEX

Explanations

elements associated with television programming and production

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

 RaisedButton

-0.15

rÃ¡n

-0.14

aku

-0.14

 inaugur

-0.14

aign

-0.14

èª

-0.14

gee

-0.14

ocl

-0.14

illon

-0.14

.MockMvc

-0.14

POSITIVE LOGITS

 talent

0.17

 Talent

0.16

Kar

0.16

rts

0.16

Tal

0.15

coil

0.15

ãģ£ãģį

0.15

 partner

0.14

ule

0.14

Aus

0.14

Activations Density 0.069%

elements associated with television programming and production

No Comments

No Known Activations