INDEX

Explanations

specific references to films and their metadata

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Urg

-0.15

quality

-0.14

bay

-0.14

Ä±rak

-0.14

 deadline

-0.14

lage

-0.14

Mis

-0.14

doz

-0.14

Ph

-0.13

POSITIVE LOGITS

ãĥ³ãĥĶ

0.16

AMERA

0.15

 seins

0.15

ÅĻiv

0.15

ÄĽst

0.15

LETTE

0.15

ouchers

0.14

_MA

0.14

inspace

0.14

codegen

0.14

Activations Density 0.007%

specific references to films and their metadata

No Comments

No Known Activations