INDEX

Explanations

references to death and associated circumstances

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

igs

-0.15

cas

-0.14

emos

-0.14

bes

-0.14

áº¯c

-0.14

ÑĩÐµÐ¼

-0.14

minus

-0.14

aniem

-0.14

awi

-0.13

ibold

-0.13

POSITIVE LOGITS

thouse

0.17

atoria

0.15

ãĤ¤ãĥ³ãĥĪ

0.14

Â£Â£

0.14

scape

0.14

ħ§

0.13

áº£

0.13

³

0.13

GC

0.13

-ln

0.13

Activations Density 0.026%

references to death and associated circumstances

No Comments

No Known Activations